Skip to content

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

1.0 KB
Raw Blame
# This is an example that demonstrates how to configure a model file.
# You can modify the configuration according to your own requirements.

# to print the register_table:
# from funasr.register import tables
# tables.print()

model: CTTransformerStreaming
model_conf:
    ignore_id: 0
    embed_unit: 256
    att_unit: 256
    dropout_rate: 0.1
    punc_list:
        - <unk>
        - _
        - ,
        - 。
        - ?
        - 、
    punc_weight:
        - 1.0
        - 1.0
        - 1.0
        - 1.0
        - 1.0
        - 1.0
    sentence_end_id: 3

encoder: SANMVadEncoder
encoder_conf:
    input_size: 256
    output_size: 256
    attention_heads: 8
    linear_units: 1024
    num_blocks: 3
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    attention_dropout_rate: 0.0
    input_layer: pe
    pos_enc_class: SinusoidalPositionEncoder
    normalize_before: true
    kernel_size: 11
    sanm_shfit: 5
    selfattention_layer_type: sanm
    padding_idx: 0

tokenizer: CharTokenizer
tokenizer_conf:
  unk_symbol: <unk>